Information Technology Reference
In-Depth Information
probabilistic semantics and fuzzy (
t-norm
-based) semantics. The choice of proba-
bilistic semantics was mostly motivated by the natural identification of the degrees
of confirmation in the rules of the system with probabilities whereas the choice of
a fuzzy semantics was mostly motivated by the natural identification of the input
values of the input symptoms in a run of the inference engine with membership
degrees in fuzzy set theory and by the inference methodology itself. In order to
set the inference process on probabilistic grounds a probabilistic interpretation of
the input values was needed and thus its natural interpretation, (arguably) more in
keeping with a fuzzy semantics, had to be overlooked. On the other hand, in order
to set the inference process fully on the grounds of a fuzzy semantics the degrees of
confirmation in the rules of the system needed to be interpreted accordingly, despite
the fact that such degrees are better represented by uncertainty measures such as
probabilities. This granted, we showed that both semantics could account well for
several steps along the inference process, in particular the attempted
t-norm
-based
fuzzy semantics -based on the decision to use the
minimum
operator as the
t-norm
-
yet, overall, none of them proved fully suitable as the intended interpretation of the
system.
Acknowledgement.
This work was partially supported by the Vienna Science and Technol-
ogy Fund (WWTF). Grant MA07-016.
References
1. Adlassnig, K.-P., Kolarz, G., Scheithauer, W., Grabner, H.: Approach to a Hospital Based
Application of a Medical Expert System. Medical Informatics 11(3), 205-223 (1986)
2. Adlassnig, K.-P., Kolarz, G.:
Effenberger, Harald and Helmut Grabner:
CADIAG:
Approaches
to
Computer-assisted
Medical
Diagnosis.
Computers
in
Biology
and
Medicine 15, 315-335 (1985)
3. Adlassnig, K.-P.: Fuzzy Set Theory in Medical Diagnosis. IEEE Transactions on Sys-
tems, Man and Cybernetics 16(2), 260-265 (1987)
4. Buchanan, B.G., Shortliffe, E.H. (eds.): Rule-Based Expert Systems: The MYCIN Ex-
periments of the Stanford Heuristic Programming Project. Addison-Wesley, Reading
(1984)
5. Castillo, E., Gutiérrez, J.M., Hadi, A.S.: Expert Systems and Probabilistic Network
Models. Springer, New York (1997)
6. Ciabattoni, A., Vetterlein, T.: On the Fuzzy (Logical) Content of CADIAG2. Fuzzy Sets
and Systems 161(14), 1941-1958 (2009)
7. Ciabattoni, A., Rusnok, P.: On the Classical Content of Monadic G
∼
and its Application
to a Fuzzy Medical Expert System. In: Proceedings of the 12th International Conference
on the Principles of Knowledge Representation and Reasoning, KR 2010 (2010)
8. Daniel, M., Hájek, P., Nguyen, P.H.: CADIAG2 and MYCIN-like systems. Artificial
Intelligence in Medicine 9, 241-259 (1997)
9. Genest, C., Zidek, J.V.: Combining Probability Distributions: A Critique and an Anno-
tated Bibliography. Statistical Science 1(1), 114-135 (1986)
10. Gerla, G.: Fuzzy Logic. Kluwer Academic Press, Dordrecht (2000)
